From c74176c0650ff3c12ee1848c1d5aa8e4dcdaed2a Mon Sep 17 00:00:00 2001 From: lishunyang12 Date: Wed, 15 Jul 2026 09:58:29 +0000 Subject: [PATCH] docs: simplify upstream-mapping table --- docs/design/skip_softmax_sage_trtllm_gen.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/design/skip_softmax_sage_trtllm_gen.md b/docs/design/skip_softmax_sage_trtllm_gen.md index 8464a4499..b7fc173a0 100644 --- a/docs/design/skip_softmax_sage_trtllm_gen.md +++ b/docs/design/skip_softmax_sage_trtllm_gen.md @@ -53,11 +53,11 @@ class TrtllmGenConfig: # mirrors TRT-LLM SkipSoftmaxAttentionCon **Maps to upstream:** -| vLLM-Omni knob | TRT-LLM / ModelOpt | FlashInfer kernel arg | -|----------------|--------------------|-----------------------| -| `sage` | SAGE (separate axis; not in `SkipSoftmaxAttentionConfig`) | `sage_block_sizes=(q,k,v)` + `bmm1_scale`/`bmm2_scale` | -| `target_sparsity` | ModelOpt calibration input → config file maps to `threshold_scale_factor` | `skip_softmax_threshold_scale_factor` (threshold = factor / seqlen) | -| `disabled_until_timestep` | — (DiT-only; not in TRT-LLM's LLM config) | host-side gate, no kernel arg | +| vLLM-Omni | TRT-LLM / ModelOpt | FlashInfer | +|-----------|--------------------|------------| +| `sage` | — | `sage_block_sizes` + `bmm1/bmm2_scale` | +| `target_sparsity` | `threshold_scale_factor` (via calibration) | `skip_softmax_threshold_scale_factor` | +| `disabled_until_timestep` | — (DiT-only) | host gate | ---